Odyssey 2012 - The Speaker and Language Recognition Workshop

Singapore
June 25-28, 2012

Variance-Spectra based Normalization for i-Vector Standard and Probabilistic Linear Discriminant Analysis

Pierre-Michel Bousquet (1), Anthony Larcher (2), Driss Matrouf (1), Jean-François Bonastre (1), Oldřich Plchot (3)

(1) University of Avignon - LIA, France
(2) Human Language Technology Department, Institute for Infocomm Research, A*STAR, Singapore
(3) Brno University of Technology, Speech@FIT, Brno, Czech Republic

I-vector extraction and Probabilistic Linear Discriminant Analysis (PLDA) has become the state-of-the-art configuration for speaker verification. Recently, Gaussian-PLDA has been improved by a preliminary length normalization of i-vectors. This normalization, known to increase the Gaussianity of the i-vector distribution, also improves performance of systems based on standard Linear Discriminant Analysis (LDA) and ”two-covariance model” scoring. But this technique follows a standardization of the i-vectors (centering and whitening ivectors based on the first and second order moments of the development data). We propose in this paper two techniques of normalization based on total, between- and within-speaker variance spectra. These ”spectral” techniques both normalize the i-vectors length for Gaussianity, but the first adapts the ivectors representation to a speaker recognition system based on LDA and two-covariance scoring when the second adapts it to a Gaussian-PLDA model. Significant performance improvements are demonstrated on the male and female telephone portion of NIST SRE 2010. Index Terms: i-vectors, probabilistic linear discriminant analysis, speaker recognition.

Full Paper

Bibliographic reference.  Bousquet, Pierre-Michel / Larcher, Anthony / Matrouf, Driss / Bonastre, Jean-François / Plchot, Oldřich (2012): "Variance-spectra based normalization for i-vector standard and probabilistic linear discriminant analysis", In Odyssey-2012, 157-164.